Problem Statement¶

In this project, we are going to predict whether a person makes over 50k a year.¶

Importing necessary Libraries¶

In [1]:
## Importing the Required Libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import warnings
warnings.filterwarnings('ignore')

Importing the Libraries and Viewing It.¶

In [2]:
df = pd.read_csv(r"C:\Users\lenovo\Desktop\adult.csv")
df.head()
Out[2]:
age workclass fnlwgt education education.num marital.status occupation relationship race sex capital.gain capital.loss hours.per.week native.country income
0 90 ? 77053 HS-grad 9 Widowed ? Not-in-family White Female 0 4356 40 United-States <=50K
1 82 Private 132870 HS-grad 9 Widowed Exec-managerial Not-in-family White Female 0 4356 18 United-States <=50K
2 66 ? 186061 Some-college 10 Widowed ? Unmarried Black Female 0 4356 40 United-States <=50K
3 54 Private 140359 7th-8th 4 Divorced Machine-op-inspct Unmarried White Female 0 3900 40 United-States <=50K
4 41 Private 264663 Some-college 10 Separated Prof-specialty Own-child White Female 0 3900 40 United-States <=50K

Collecting Extra Information about the DataSet¶

In [3]:
df.shape
Out[3]:
(32561, 15)
In [4]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 32561 entries, 0 to 32560
Data columns (total 15 columns):
 #   Column          Non-Null Count  Dtype 
---  ------          --------------  ----- 
 0   age             32561 non-null  int64 
 1   workclass       32561 non-null  object
 2   fnlwgt          32561 non-null  int64 
 3   education       32561 non-null  object
 4   education.num   32561 non-null  int64 
 5   marital.status  32561 non-null  object
 6   occupation      32561 non-null  object
 7   relationship    32561 non-null  object
 8   race            32561 non-null  object
 9   sex             32561 non-null  object
 10  capital.gain    32561 non-null  int64 
 11  capital.loss    32561 non-null  int64 
 12  hours.per.week  32561 non-null  int64 
 13  native.country  32561 non-null  object
 14  income          32561 non-null  object
dtypes: int64(6), object(9)
memory usage: 3.7+ MB
In [5]:
## Checking for Null Values in DataSet
df.isnull().sum()
Out[5]:
age               0
workclass         0
fnlwgt            0
education         0
education.num     0
marital.status    0
occupation        0
relationship      0
race              0
sex               0
capital.gain      0
capital.loss      0
hours.per.week    0
native.country    0
income            0
dtype: int64
In [6]:
## Checking for unique values
df.nunique()
Out[6]:
age                  73
workclass             9
fnlwgt            21648
education            16
education.num        16
marital.status        7
occupation           15
relationship          6
race                  5
sex                   2
capital.gain        119
capital.loss         92
hours.per.week       94
native.country       42
income                2
dtype: int64

Exploratory Data Analysis ( EDA )¶

In [7]:
df.describe().T
Out[7]:
count mean std min 25% 50% 75% max
age 32561.0 38.581647 13.640433 17.0 28.0 37.0 48.0 90.0
fnlwgt 32561.0 189778.366512 105549.977697 12285.0 117827.0 178356.0 237051.0 1484705.0
education.num 32561.0 10.080679 2.572720 1.0 9.0 10.0 12.0 16.0
capital.gain 32561.0 1077.648844 7385.292085 0.0 0.0 0.0 0.0 99999.0
capital.loss 32561.0 87.303830 402.960219 0.0 0.0 0.0 0.0 4356.0
hours.per.week 32561.0 40.437456 12.347429 1.0 40.0 40.0 45.0 99.0
In [8]:
df['workclass'].value_counts()
Out[8]:
Private             22696
Self-emp-not-inc     2541
Local-gov            2093
?                    1836
State-gov            1298
Self-emp-inc         1116
Federal-gov           960
Without-pay            14
Never-worked            7
Name: workclass, dtype: int64
In [9]:
df['occupation'].value_counts()
Out[9]:
Prof-specialty       4140
Craft-repair         4099
Exec-managerial      4066
Adm-clerical         3770
Sales                3650
Other-service        3295
Machine-op-inspct    2002
?                    1843
Transport-moving     1597
Handlers-cleaners    1370
Farming-fishing       994
Tech-support          928
Protective-serv       649
Priv-house-serv       149
Armed-Forces            9
Name: occupation, dtype: int64
In [10]:
df['native.country'].value_counts()
Out[10]:
United-States                 29170
Mexico                          643
?                               583
Philippines                     198
Germany                         137
Canada                          121
Puerto-Rico                     114
El-Salvador                     106
India                           100
Cuba                             95
England                          90
Jamaica                          81
South                            80
China                            75
Italy                            73
Dominican-Republic               70
Vietnam                          67
Guatemala                        64
Japan                            62
Poland                           60
Columbia                         59
Taiwan                           51
Haiti                            44
Iran                             43
Portugal                         37
Nicaragua                        34
Peru                             31
Greece                           29
France                           29
Ecuador                          28
Ireland                          24
Hong                             20
Cambodia                         19
Trinadad&Tobago                  19
Laos                             18
Thailand                         18
Yugoslavia                       16
Outlying-US(Guam-USVI-etc)       14
Hungary                          13
Honduras                         13
Scotland                         12
Holand-Netherlands                1
Name: native.country, dtype: int64
In [11]:
df['marital.status'].value_counts()
Out[11]:
Married-civ-spouse       14976
Never-married            10683
Divorced                  4443
Separated                 1025
Widowed                    993
Married-spouse-absent      418
Married-AF-spouse           23
Name: marital.status, dtype: int64
In [12]:
df['sex'].value_counts()
Out[12]:
Male      21790
Female    10771
Name: sex, dtype: int64
In [13]:
df['race'].value_counts()
Out[13]:
White                 27816
Black                  3124
Asian-Pac-Islander     1039
Amer-Indian-Eskimo      311
Other                   271
Name: race, dtype: int64
In [14]:
df['income'].value_counts()
Out[14]:
<=50K    24720
>50K      7841
Name: income, dtype: int64
In [15]:
df['education'].value_counts()
Out[15]:
HS-grad         10501
Some-college     7291
Bachelors        5355
Masters          1723
Assoc-voc        1382
11th             1175
Assoc-acdm       1067
10th              933
7th-8th           646
Prof-school       576
9th               514
12th              433
Doctorate         413
5th-6th           333
1st-4th           168
Preschool          51
Name: education, dtype: int64
In [16]:
sns.countplot(df['income'], palette='coolwarm', hue='relationship', data=df);
In [17]:
# Filling ? values
# replacing the values with mode

df['workclass'] = df['workclass'].replace('?', 'Private')
df['occupation'] = df['occupation'].replace('?', 'Prof-specialty')
df['native.country'] = df['native.country'].replace('?', 'United-States')
In [18]:
df.head()
Out[18]:
age workclass fnlwgt education education.num marital.status occupation relationship race sex capital.gain capital.loss hours.per.week native.country income
0 90 Private 77053 HS-grad 9 Widowed Prof-specialty Not-in-family White Female 0 4356 40 United-States <=50K
1 82 Private 132870 HS-grad 9 Widowed Exec-managerial Not-in-family White Female 0 4356 18 United-States <=50K
2 66 Private 186061 Some-college 10 Widowed Prof-specialty Unmarried Black Female 0 4356 40 United-States <=50K
3 54 Private 140359 7th-8th 4 Divorced Machine-op-inspct Unmarried White Female 0 3900 40 United-States <=50K
4 41 Private 264663 Some-college 10 Separated Prof-specialty Own-child White Female 0 3900 40 United-States <=50K

Feature Engineering¶

In [19]:
# education Category

df.education= df.education.replace(['Preschool', '1st-4th', '5th-6th', '7th-8th', '9th','10th', '11th', '12th'], 'school')
df.education = df.education.replace('HS-grad', 'high school')
df.education = df.education.replace(['Assoc-voc', 'Assoc-acdm', 'Prof-school', 'Some-college'], 'higher')
df.education = df.education.replace('Bachelors', 'undergrad')
df.education = df.education.replace('Masters', 'grad')
df.education = df.education.replace('Doctorate', 'doc')
In [20]:
# martial status

df['marital.status']= df['marital.status'].replace(['Married-civ-spouse', 'Married-AF-spouse'], 'married')
df['marital.status']= df['marital.status'].replace(['Never-married'], 'not-married')
df['marital.status']= df['marital.status'].replace(['Divorced', 'Separated','Widowed',
                                                   'Married-spouse-absent'], 'other')
In [21]:
# income

df.income = df.income.replace('<=50K', 0)
df.income = df.income.replace('>50K', 1)
In [22]:
df.head()
Out[22]:
age workclass fnlwgt education education.num marital.status occupation relationship race sex capital.gain capital.loss hours.per.week native.country income
0 90 Private 77053 high school 9 other Prof-specialty Not-in-family White Female 0 4356 40 United-States 0
1 82 Private 132870 high school 9 other Exec-managerial Not-in-family White Female 0 4356 18 United-States 0
2 66 Private 186061 higher 10 other Prof-specialty Unmarried Black Female 0 4356 40 United-States 0
3 54 Private 140359 school 4 other Machine-op-inspct Unmarried White Female 0 3900 40 United-States 0
4 41 Private 264663 higher 10 other Prof-specialty Own-child White Female 0 3900 40 United-States 0
In [23]:
df['marital.status'].value_counts()
Out[23]:
married        14999
not-married    10683
other           6879
Name: marital.status, dtype: int64
In [24]:
df['education'].value_counts()
Out[24]:
high school    10501
higher         10316
undergrad       5355
school          4253
grad            1723
doc              413
Name: education, dtype: int64
In [25]:
df.corr()
Out[25]:
age fnlwgt education.num capital.gain capital.loss hours.per.week income
age 1.000000 -0.076646 0.036527 0.077674 0.057775 0.068756 0.234037
fnlwgt -0.076646 1.000000 -0.043195 0.000432 -0.010252 -0.018768 -0.009463
education.num 0.036527 -0.043195 1.000000 0.122630 0.079923 0.148123 0.335154
capital.gain 0.077674 0.000432 0.122630 1.000000 -0.031615 0.078409 0.223329
capital.loss 0.057775 -0.010252 0.079923 -0.031615 1.000000 0.054256 0.150526
hours.per.week 0.068756 -0.018768 0.148123 0.078409 0.054256 1.000000 0.229689
income 0.234037 -0.009463 0.335154 0.223329 0.150526 0.229689 1.000000
In [26]:
sns.heatmap(df.corr(), annot=True);
In [27]:
df.hist(figsize=(12,12), layout=(3,3), sharex=False);
In [28]:
df.plot(kind='box', figsize=(12,12), layout=(3,3), sharex=False, subplots=True);
In [29]:
px.pie(df, values='education.num', names='education', title='% of edu', 
      color_discrete_sequence = px.colors.qualitative.T10)
In [30]:
sns.countplot(df['education'], hue='sex', data=df, palette='seismic');

Model Building¶

In [31]:
X= df.drop(['income'], axis=1)
y = df['income']

Feature Scaling¶

In [32]:
from sklearn.preprocessing import StandardScaler, LabelEncoder
In [33]:
df1= df.copy()
df1= df1.apply(LabelEncoder().fit_transform)
df1.head()
Out[33]:
age workclass fnlwgt education education.num marital.status occupation relationship race sex capital.gain capital.loss hours.per.week native.country income
0 72 3 2649 2 8 2 9 1 4 0 0 91 39 38 0
1 65 3 6514 2 8 2 3 1 4 0 0 91 17 38 0
2 49 3 11175 3 9 2 9 4 2 0 0 91 39 38 0
3 37 3 7009 4 3 2 6 4 4 0 0 90 39 38 0
4 24 3 16850 3 9 2 9 3 4 0 0 90 39 38 0
In [34]:
ss= StandardScaler().fit(df1.drop('income', axis=1))
In [35]:
X= ss.transform(df1.drop('income', axis=1))
y= df['income']

Splitting data into train & test¶

In [36]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=40)

Logistic Regression¶

In [37]:
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

lr = LogisticRegression()

model = lr.fit(X_train, y_train)
prediction = model.predict(X_test)

print("Acc on training data: {:,.3f}".format(lr.score(X_train, y_train)))
print("Acc on test data: {:,.3f}".format(lr.score(X_test, y_test)))

Acc on training data: 0.839
Acc on test data: 0.836

Random Forest Classifier¶

In [38]:
from sklearn.ensemble import RandomForestClassifier

rfc = RandomForestClassifier()

model1 = rfc.fit(X_train, y_train)
prediction1 = model1.predict(X_test)

print("Acc on training data: {:,.3f}".format(rfc.score(X_train, y_train)))
print("Acc on test data: {:,.3f}".format(rfc.score(X_test, y_test)))

Acc on training data: 1.000
Acc on test data: 0.854

Model Evaluation¶

In [39]:
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
In [40]:
print(confusion_matrix(y_test, prediction1))

[[6883  523]
 [ 903 1460]]
In [41]:
print(classification_report(y_test, prediction1))

              precision    recall  f1-score   support

           0       0.88      0.93      0.91      7406
           1       0.74      0.62      0.67      2363

    accuracy                           0.85      9769
   macro avg       0.81      0.77      0.79      9769
weighted avg       0.85      0.85      0.85      9769
In [42]:
#Precision: tp/tp+fp

print('Precision =' , 10332/(10332+1286))

Precision = 0.8893096918574626
In [43]:
# recall= tp/tp+fn

print('Recall =', 10332/(10332+806))

Recall = 0.9276351230023343

for other class : 1 (>50K)¶

In [44]:
print('Precision = ', 2229/(2229+806))

Precision =  0.7344316309719934
In [45]:
print('Recall= ', 2229/(2229+1286))

Recall=  0.6341394025604552

                         - - - - - - - - X X X X X X X X - - - - - - - -